# When should a small model ask for help?

*Illustrative: an example paper, not a published article.*

Mira Vale (example author). Efficient inference. Example issue: The inference issue.

## Abstract

Can a routing threshold keep a large model off routine cases while sending it the decisions that need another read? An encoder makes the first prediction. Moving a confidence threshold changes the fraction of cases a second model sees. In 100 constructed example cases, a strict threshold sends 12 to the second model, a middle one 29 and a loose one 57.

## Selection record (illustrative)

Cohort of 100 papers. Expected impact: 8th of 100. Talk interest: 2nd of 100. Finalist; full reviews credited the measured saving and named the missing test on a new domain.

## Limitations

The trade-off depends on how well confidence holds up on new data. The illustrated routing counts do not establish accuracy on future traffic.

## Cite this example

Vale, M. When should a small model ask for help? TenPeers, example issue (illustrative, not published). Identifier: assigned on publication.

Source: https://tenpeers.com/journal/sample-issue/small-model-help/
